Search Results for author: Ming Jin

Found 103 papers, 40 papers with code

Continuous Evolution Pool: Taming Recurring Concept Drift in Online Time Series Forecasting

1 code implementation28 May 2025 Tianxiang Zhan, Ming Jin, Yuanpeng He, Yuxuan Liang, Yong Deng, Shirui Pan

Recurring concept drift, a type of concept drift in which previously observed data patterns reappear after some time, is one of the most prevalent types of concept drift in time series.

Time Series Time Series Forecasting

Few-Shot Test-Time Optimization Without Retraining for Semiconductor Recipe Generation and Beyond

no code implementations21 May 2025 Shangding Gu, Donghao Ying, Ming Jin, Yu Joe Lu, Jun Wang, Javad Lavaei, Costas Spanos

In contrast to existing methods that rely on adjusting model parameters, MFL leverages a lightweight reverse model to iteratively search for optimal inputs, enabling efficient adaptation to new objectives under deployment constraints.

Bayesian Optimization Recipe Generation

T2S: High-resolution Time Series Generation with Text-to-Series Diffusion Models

1 code implementation5 May 2025 Yunfeng Ge, Jiawei Li, Yiji Zhao, Haomin Wen, Zhao Li, Meikang Qiu, Hongyan Li, Ming Jin, Shirui Pan

Text-to-Time Series generation holds significant potential to address challenges such as data sparsity, imbalance, and limited availability of multimodal time series datasets across domains.

Time Series Time Series Generation

Foundation Models for Spatio-Temporal Data Science: A Tutorial and Survey

1 code implementation12 Mar 2025 Yuxuan Liang, Haomin Wen, Yutong Xia, Ming Jin, Bin Yang, Flora Salim, Qingsong Wen, Shirui Pan, Gao Cong

Spatio-Temporal (ST) data science, which includes sensing, managing, and mining large-scale data across space and time, is fundamental to understanding complex systems in domains such as urban computing, climate science, and intelligent transportation.

Management

Backtracking for Safety

no code implementations11 Mar 2025 Bilgehan Sel, Dingcheng Li, Phillip Wallis, Vaishakh Keshava, Ming Jin, Siddhartha Reddy Jonnalagadda

Large language models (LLMs) have demonstrated remarkable capabilities across various tasks, but ensuring their safety and alignment with human values remains crucial.

Safety Alignment

Robust Gymnasium: A Unified Modular Benchmark for Robust Reinforcement Learning

no code implementations27 Feb 2025 Shangding Gu, Laixi Shi, Muning Wen, Ming Jin, Eric Mazumdar, Yuejie Chi, Adam Wierman, Costas Spanos

Driven by inherent uncertainty and the sim-to-real gap, robust reinforcement learning (RL) seeks to improve resilience against the complexity and variability in agent-environment sequential interactions.

reinforcement-learning Reinforcement Learning +1

TimeDistill: Efficient Long-Term Time Series Forecasting with MLP via Cross-Architecture Distillation

1 code implementation20 Feb 2025 Juntong Ni, Zewen Liu, Shiyu Wang, Ming Jin, Wei Jin

Based on this observation, we introduce TimeDistill, a cross-architecture KD framework that transfers these patterns from teacher models (e. g., Transformers, CNNs) to MLP.

Data Augmentation Knowledge Distillation +2

Time-VLM: Exploring Multimodal Vision-Language Models for Augmented Time Series Forecasting

no code implementations6 Feb 2025 Siru Zhong, Weilin Ruan, Ming Jin, Huan Li, Qingsong Wen, Yuxuan Liang

Recent advancements in time series forecasting have explored augmenting models with text or vision modalities to improve accuracy.

Time Series Time Series Forecasting

Detecting Zero-Day Attacks in Digital Substations via In-Context Learning

no code implementations27 Jan 2025 Faizan Manzoor, Vanshaj Khattar, Akila Herath, Clifton Black, Matthew C Nielsen, Junho Hong, Chen-Ching Liu, Ming Jin

The occurrences of cyber attacks on the power grids have been increasing every year, with novel attack techniques emerging every year.

In-Context Learning

LLMs Can Plan Only If We Tell Them

no code implementations23 Jan 2025 Bilgehan Sel, Ruoxi Jia, Ming Jin

Large language models (LLMs) have demonstrated significant capabilities in natural language processing and reasoning, yet their effectiveness in autonomous planning has been under debate.

Augmenting Minds or Automating Skills: The Differential Role of Human Capital in Generative AI's Impact on Creative Tasks

no code implementations5 Dec 2024 Meiling Huang, Ming Jin, Ning li

This framework elucidates how AI shifts the locus of creative advantage from specialized expertise to broader cognitive adaptability.

FAS for Secure and Covert Communications

no code implementations14 Nov 2024 Junteng Yao, Liangxiao Xin, Tuo Wu, Ming Jin, Kai-Kit Wong, Chau Yuen, Hyundong Shin

This letter considers a fluid antenna system (FAS)-aided secure and covert communication system, where the transmitter adjusts multiple fluid antennas' positions to achieve secure and covert transmission under the threat of an eavesdropper and the detection of a warden.

Position

FAS-Driven Spectrum Sensing for Cognitive Radio Networks

no code implementations13 Nov 2024 Junteng Yao, Ming Jin, Tuo Wu, Maged Elkashlan, Chau Yuen, Kai-Kit Wong, George K. Karagiannidis, Hyundong Shin

Cognitive radio (CR) networks face significant challenges in spectrum sensing, especially under spectrum scarcity.

EffiCANet: Efficient Time Series Forecasting with Convolutional Attention

no code implementations7 Nov 2024 Xinxing Zhou, Jiaqi Ye, Shubao Zhao, Ming Jin, Chengyi Yang, Yanlong Wen, Xiaojie Yuan

The exponential growth of multivariate time series data from sensor networks in domains like industrial monitoring and smart cities requires efficient and accurate forecasting models.

Computational Efficiency Time Series +1

Rethinking the Uncertainty: A Critical Review and Analysis in the Era of Large Language Models

no code implementations26 Oct 2024 Mohammad Beigi, Sijia Wang, Ying Shen, Zihao Lin, Adithya Kulkarni, Jianfeng He, Feng Chen, Ming Jin, Jin-Hee Cho, Dawei Zhou, Chang-Tien Lu, Lifu Huang

In recent years, Large Language Models (LLMs) have become fundamental to a broad spectrum of artificial intelligence applications.

TimeMixer++: A General Time Series Pattern Machine for Universal Predictive Analysis

2 code implementations21 Oct 2024 Shiyu Wang, Jiawei Li, Xiaoming Shi, Zhou Ye, Baichuan Mo, Wenze Lin, Shengtong Ju, Zhixuan Chu, Ming Jin

Specifically, we introduce a general-purpose TSPM that processes multi-scale time series using (1) multi-resolution time imaging (MRTI), (2) time image decomposition (TID), (3) multi-scale mixing (MCM), and (4) multi-resolution mixing (MRM) to extract comprehensive temporal patterns.

Anomaly Detection Imputation +2

Towards Neural Scaling Laws for Time Series Foundation Models

1 code implementation16 Oct 2024 Qingren Yao, Chao-Han Huck Yang, Renhe Jiang, Yuxuan Liang, Ming Jin, Shirui Pan

In this work, we examine two common TSFM architectures, encoder-only and decoder-only Transformers, and investigate their scaling behavior on both ID and OOD data.

Decoder Time Series

EvoFA: Evolvable Fast Adaptation for EEG Emotion Recognition

no code implementations24 Sep 2024 Ming Jin, Danni Zhang, Gangming Zhao, Changde Du, Jinpeng Li

While numerous domain adaptation (DA) approaches have been proposed in recent years to address this issue, their reliance on large amounts of target data for calibration restricts them to offline scenarios, rendering them unsuitable for real-time applications.

Domain Adaptation EEG +2

Time-MoE: Billion-Scale Time Series Foundation Models with Mixture of Experts

1 code implementation24 Sep 2024 Xiaoming Shi, Shiyu Wang, Yuqi Nie, Dianqi Li, Zhou Ye, Qingsong Wen, Ming Jin

However, despite the success of large-scale pre-training in language and vision domains, pre-trained time series models remain limited in scale and operate at a high cost, hindering the development of larger capable forecasting models in real-world applications.

Computational Efficiency Mixture-of-Experts +2

BCRLB Under the Fusion Extended Kalman Filter

no code implementations24 Sep 2024 Mushen Lin, Fenggang Yan, Lingda Ren, Xiangtian Meng, Maria Greco, Fulvio Gini, Ming Jin

However, the data measured by radar nodes contains noise, clutter, and false targets, making it difficult for the fusion center to directly establish the association between radar measurements and real targets.

Towards Universal Large-Scale Foundational Model for Natural Gas Demand Forecasting

no code implementations24 Sep 2024 Xinxing Zhou, Jiaqi Ye, Shubao Zhao, Ming Jin, Zhaoxiang Hou, Chengyi Yang, Zengxiang Li, Yanlong Wen, Xiaojie Yuan

In the context of global energy strategy, accurate natural gas demand forecasting is crucial for ensuring efficient resource allocation and operational planning.

Contrastive Learning Demand Forecasting

DiPT: Enhancing LLM reasoning through diversified perspective-taking

no code implementations10 Sep 2024 Hoang Anh Just, Mahavir Dabas, Lifu Huang, Ming Jin, Ruoxi Jia

This approach allows the model to gain a deeper understanding of the problem's context and identify the most effective solution path during the inference stage.

Language Modeling Language Modelling

Optimization Solution Functions as Deterministic Policies for Offline Reinforcement Learning

no code implementations27 Aug 2024 Vanshaj Khattar, Ming Jin

Offline reinforcement learning (RL) is a promising approach for many control applications but faces challenges such as limited data coverage and value function overestimation.

Offline RL reinforcement-learning +2

FAS-RIS Communication: Model, Analysis, and Optimization

no code implementations24 Aug 2024 Junteng Yao, Jianchao Zheng, Tuo Wu, Ming Jin, Chau Yuen, Kai-Kit Wong, Fumiyuki Adachi

This correspondence investigates the novel fluid antenna system (FAS) technology, combining with reconfigurable intelligent surface (RIS) for wireless communications, where a base station (BS) communicates with a FAS-enabled user with the assistance of a RIS.

model

Full-Duplex ISAC-Enabled D2D Underlaid Cellular Networks: Joint Transceiver Beamforming and Power Allocation

no code implementations21 Aug 2024 Tao Jiang, Ming Jin, Qinghua Guo, Yinhong Liu, Yaming Li

Integrating device-to-device (D2D) communication into cellular networks can significantly reduce the transmission burden on base stations (BSs).

Integrated sensing and communication ISAC

FAS vs. ARIS: Which Is More Important for FAS-ARIS Communication Systems?

no code implementations17 Aug 2024 Junteng Yao, Liaoshi Zhou, Tuo Wu, Ming Jin, Chongwen Huang, Chau Yuen

We introduce an alternating optimization (AO) algorithm incorporating majorization-minimization (MM), successive convex approximation (SCA), and sequential rank-one constraint relaxation (SRCR) to tackle the non-convex challenges inherent in these systems.

DyG-Mamba: Continuous State Space Modeling on Dynamic Graphs

no code implementations13 Aug 2024 Dongyuan Li, Shiyin Tan, Ying Zhang, Ming Jin, Shirui Pan, Manabu Okumura, Renhe Jiang

Dynamic graph learning aims to uncover evolutionary laws in real-world systems, enabling accurate social recommendation (link prediction) or early detection of cancer cells (classification).

Dynamic Link Prediction Dynamic Node Classification +5

A Hypothesis on Black Swan in Unchanging Environments

no code implementations25 Jul 2024 Hyunin Lee, Chanwoo Park, David Abel, Ming Jin

Black swan events are statistically rare occurrences that carry extremely high risks.

Data-Centric Human Preference Optimization with Rationales

1 code implementation19 Jul 2024 Hoang Anh Just, Ming Jin, Anit Sahu, Huy Phan, Ruoxi Jia

Reinforcement learning from human feedback plays a crucial role in aligning language models towards human preferences, traditionally represented through comparisons between pairs or sets of responses within a given context.

Hallucination

Fluid Antenna-Assisted Simultaneous Wireless Information and Power Transfer Systems

no code implementations16 Jul 2024 Liaoshi Zhou, Junteng Yao, Tuo Wu, Ming Jin, Chau Yuen, Fumiyuki Adachi

Unlike traditional SWIPT systems with fixed-position antennas (FPAs), our FA-assisted system enables dynamic reconfiguration of the radio propagation environment by adjusting the positions of FAs.

A Framework of FAS-RIS Systems: Performance Analysis and Throughput Optimization

no code implementations11 Jul 2024 Junteng Yao, Xiazhi Lai, Kangda Zhi, Tuo Wu, Ming Jin, Cunhua Pan, Maged Elkashlan, Chau Yuen, Kai-Kit Wong

Then, to address the possible high computational complexity in the gradient algorithm, we approximate the objective function and confirm a unique optimal solution accessible through a bisection search method.

InternalInspector $I^2$: Robust Confidence Estimation in LLMs through Internal States

no code implementations17 Jun 2024 Mohammad Beigi, Ying Shen, Runing Yang, Zihao Lin, Qifan Wang, Ankith Mohan, Jianfeng He, Ming Jin, Chang-Tien Lu, Lifu Huang

Despite their vast capabilities, Large Language Models (LLMs) often struggle with generating reliable outputs, frequently producing high-confidence inaccuracies known as hallucinations.

Benchmarking Contrastive Learning +4

Fairness-Aware Meta-Learning via Nash Bargaining

no code implementations11 Jun 2024 Yi Zeng, Xuelin Yang, Li Chen, Cristian Canton Ferrer, Ming Jin, Michael I. Jordan, Ruoxi Jia

To address issues of group-level fairness in machine learning, it is natural to adjust model parameters based on specific fairness objectives over a sensitive-attributed validation set.

Fairness image-classification +3

Enhancing Efficiency of Safe Reinforcement Learning via Sample Manipulation

1 code implementation31 May 2024 Shangding Gu, Laixi Shi, Yuhao Ding, Alois Knoll, Costas Spanos, Adam Wierman, Ming Jin

Safe reinforcement learning (RL) is crucial for deploying RL agents in real-world applications, as it aims to maximize long-term rewards while satisfying safety constraints.

MuJoCo reinforcement-learning +3

A CMDP-within-online framework for Meta-Safe Reinforcement Learning

no code implementations26 May 2024 Vanshaj Khattar, Yuhao Ding, Bilgehan Sel, Javad Lavaei, Ming Jin

Meta-reinforcement learning has widely been used as a learning-to-learn framework to solve unseen tasks with limited experience.

Meta-Learning Meta Reinforcement Learning +3

Safe and Balanced: A Framework for Constrained Multi-Objective Reinforcement Learning

1 code implementation26 May 2024 Shangding Gu, Bilgehan Sel, Yuhao Ding, Lu Wang, QIngwei Lin, Alois Knoll, Ming Jin

In numerous reinforcement learning (RL) problems involving safety-critical systems, a key challenge lies in balancing multiple objectives while simultaneously meeting all stringent safety constraints.

Multi-Objective Reinforcement Learning reinforcement-learning +1

Pausing Policy Learning in Non-stationary Reinforcement Learning

1 code implementation25 May 2024 Hyunin Lee, Ming Jin, Javad Lavaei, Somayeh Sojoudi

Real-time inference is a challenge of real-world reinforcement learning due to temporal differences in time-varying environments: the system collects data from the past, updates the decision model in the present, and deploys it in the future.

reinforcement-learning Reinforcement Learning

Skin-in-the-Game: Decision Making via Multi-Stakeholder Alignment in LLMs

no code implementations21 May 2024 Bilgehan Sel, Priya Shanmugasundaram, Mohammad Kachuee, Kun Zhou, Ruoxi Jia, Ming Jin

Large Language Models (LLMs) have shown remarkable capabilities in tasks such as summarization, arithmetic reasoning, and question answering.

Arithmetic Reasoning Decision Making +1

Preparing for Black Swans: The Antifragility Imperative for Machine Learning

no code implementations18 May 2024 Ming Jin

Operating safely and reliably despite continual distribution shifts is vital for high-stakes machine learning applications.

Continual Learning Decision Making +4

A Survey on Diffusion Models for Time Series and Spatio-Temporal Data

2 code implementations29 Apr 2024 Yiyuan Yang, Ming Jin, Haomin Wen, Chaoli Zhang, Yuxuan Liang, Lintao Ma, Yi Wang, Chenghao Liu, Bin Yang, Zenglin Xu, Jiang Bian, Shirui Pan, Qingsong Wen

Conditioned models, on the other hand, utilize extra information to enhance performance and are similarly divided for both predictive and generative tasks.

Anomaly Detection Imputation +1

Foundation Models for Time Series Analysis: A Tutorial and Survey

2 code implementations21 Mar 2024 Yuxuan Liang, Haomin Wen, Yuqi Nie, Yushan Jiang, Ming Jin, Dongjin Song, Shirui Pan, Qingsong Wen

Time series analysis stands as a focal point within the data mining community, serving as a cornerstone for extracting valuable insights crucial to a myriad of real-world applications.

Survey Time Series +1

Joint Optimization for Achieving Covertness in MIMO Over-the-Air Computation Networks

no code implementations15 Mar 2024 Junteng Yao, Tuo Wu, Ming Jin, Cunhua Pan, Quanzhong Li, Jinhong Yuan

This paper investigates covert data transmission within a multiple-input multiple-output (MIMO) over-the-air computation (AirComp) network, where sensors transmit data to the access point (AP) while guaranteeing covertness to the warden (Willie).

TeaMs-RL: Teaching LLMs to Generate Better Instruction Datasets via Reinforcement Learning

1 code implementation13 Mar 2024 Shangding Gu, Alois Knoll, Ming Jin

The development of Large Language Models (LLMs) often confronts challenges stemming from the heavy reliance on human annotators in the reinforcement learning with human feedback (RLHF) framework, or the frequent and costly external queries tied to the self-instruct paradigm.

reinforcement-learning Reinforcement Learning +1

Exploring Fairness for FAS-assisted Communication Systems: from NOMA to OMA

no code implementations1 Mar 2024 Junteng Yao, Liaoshi Zhou, Tuo Wu, Ming Jin, Cunhua Pan, Maged Elkashlan, Kai-Kit Wong

This paper addresses the fairness issue within fluid antenna system (FAS)-assisted non-orthogonal multiple access (NOMA) and orthogonal multiple access (OMA) systems, where a single fixed-antenna base station (BS) transmits superposition-coded signals to two users, each with a single fluid antenna.

Fairness

Attractor Memory for Long-Term Time Series Forecasting: A Chaos Perspective

1 code implementation18 Feb 2024 Jiaxi Hu, Yuehong Hu, Wei Chen, Ming Jin, Shirui Pan, Qingsong Wen, Yuxuan Liang

In long-term time series forecasting (LTSF) tasks, an increasing number of models have acknowledged that discrete time series originate from continuous dynamic systems and have attempted to model their dynamical structures.

Time Series Time Series Forecasting

The Mirrored Influence Hypothesis: Efficient Data Influence Estimation by Harnessing Forward Passes

1 code implementation CVPR 2024 Myeongseob Ko, Feiyang Kang, Weiyan Shi, Ming Jin, Zhou Yu, Ruoxi Jia

Inspired by this, we introduce a new method for estimating the influence of training data, which requires calculating gradients for specific test samples, paired with a forward pass for each training point.

Memorization

Position: What Can Large Language Models Tell Us about Time Series Analysis

2 code implementations5 Feb 2024 Ming Jin, Yifan Zhang, Wei Chen, Kexin Zhang, Yuxuan Liang, Bin Yang, Jindong Wang, Shirui Pan, Qingsong Wen

Time series analysis is essential for comprehending the complexities inherent in various realworld systems and applications.

Decision Making Position +3

Graph Spatiotemporal Process for Multivariate Time Series Anomaly Detection with Missing Values

no code implementations11 Jan 2024 Yu Zheng, Huan Yee Koh, Ming Jin, Lianhua Chi, Haishuai Wang, Khoa T. Phan, Yi-Ping Phoebe Chen, Shirui Pan, Wei Xiang

However, real-world time series data is usually not well-structured, posting significant challenges to existing approaches: (1) The existence of missing values in multivariate time series data along variable and time dimensions hinders the effective modeling of interwoven spatial and temporal dependencies, resulting in important patterns being overlooked during model training; (2) Anomaly scoring with irregularly-sampled observations is less explored, making it difficult to use existing detectors for multivariate series without fully-observed values.

Anomaly Detection Missing Values +2

Improving Intrusion Detection with Domain-Invariant Representation Learning in Latent Space

no code implementations28 Dec 2023 Padmaksha Roy, Tyler Cody, Himanshu Singhal, Kevin Choi, Ming Jin

Domain generalization focuses on leveraging knowledge from multiple related domains with ample training data and labels to enhance inference on unseen in-distribution (IN) and out-of-distribution (OOD) domains.

Domain Generalization Intrusion Detection +2

Large Models for Time Series and Spatio-Temporal Data: A Survey and Outlook

6 code implementations16 Oct 2023 Ming Jin, Qingsong Wen, Yuxuan Liang, Chaoli Zhang, Siqiao Xue, Xue Wang, James Zhang, Yi Wang, Haifeng Chen, XiaoLi Li, Shirui Pan, Vincent S. Tseng, Yu Zheng, Lei Chen, Hui Xiong

In this survey, we offer a comprehensive and up-to-date review of large models tailored (or adapted) for time series and spatio-temporal data, spanning four key facets: data types, model categories, model scopes, and application areas/tasks.

Time Series Time Series Analysis

Proactive Monitoring via Jamming in Fluid Antenna Systems

no code implementations11 Oct 2023 Junteng Yao, Tuo Wu, Xiazhi Lai, Ming Jin, Cunhua Pan, Maged Elkashlan, Kai-Kit Wong

Our objective is to maximize the average monitoring rate, whose expression involves the integral of the first-order Marcum $Q$ function.

Position

Practical Membership Inference Attacks Against Large-Scale Multi-Modal Models: A Pilot Study

1 code implementation ICCV 2023 Myeongseob Ko, Ming Jin, Chenguang Wang, Ruoxi Jia

Furthermore, our enhanced attacks outperform the baseline across multiple models and datasets, with the weakly supervised attack demonstrating an average-case performance improvement of $17\%$ and being at least $7$X more effective at low false-positive rates.

Tempo Adaptation in Non-stationary Reinforcement Learning

1 code implementation NeurIPS 2023 Hyunin Lee, Yuhao Ding, Jongmin Lee, Ming Jin, Javad Lavaei, Somayeh Sojoudi

In the context of the time-desynchronized environment, however, the agent at time $t_{k}$ allocates $\Delta t$ for trajectory generation and training, subsequently moves to the next episode at $t_{k+1}=t_{k}+\Delta t$.

reinforcement-learning Reinforcement Learning +1

Message Passing Based Block Sparse Signal Recovery for DOA Estimation Using Large Arrays

no code implementations1 Sep 2023 Yiwen Mao, Dawei Gao, Qinghua Guo, Ming Jin

This work deals with directional of arrival (DOA) estimation with a large antenna array.

Algorithm of Thoughts: Enhancing Exploration of Ideas in Large Language Models

no code implementations20 Aug 2023 Bilgehan Sel, Ahmad Al-Tawaha, Vanshaj Khattar, Ruoxi Jia, Ming Jin

Current literature, aiming to surpass the "Chain-of-Thought" approach, often resorts to external modi operandi involving halting, modifying, and then resuming the generation process to boost Large Language Models' (LLMs) reasoning capacities.

In-Context Learning

A Human-on-the-Loop Optimization Autoformalism Approach for Sustainability

no code implementations20 Aug 2023 Ming Jin, Bilgehan Sel, Fnu Hardeep, Wotao Yin

This paper outlines a natural conversational approach to solving personalized energy-related problems using large language models (LLMs).

Correlation-aware Spatial-Temporal Graph Learning for Multivariate Time-series Anomaly Detection

1 code implementation17 Jul 2023 Yu Zheng, Huan Yee Koh, Ming Jin, Lianhua Chi, Khoa T. Phan, Shirui Pan, Yi-Ping Phoebe Chen, Wei Xiang

To overcome these limitations, we propose a novel method, correlation-aware spatial-temporal graph learning (termed CST-GL), for time series anomaly detection.

Anomaly Detection Graph Learning +3

A Survey on Graph Neural Networks for Time Series: Forecasting, Classification, Imputation, and Anomaly Detection

1 code implementation7 Jul 2023 Ming Jin, Huan Yee Koh, Qingsong Wen, Daniele Zambon, Cesare Alippi, Geoffrey I. Webb, Irwin King, Shirui Pan

In this survey, we provide a comprehensive review of graph neural networks for time series analysis (GNN4TS), encompassing four fundamental dimensions: forecasting, classification, anomaly detection, and imputation.

Anomaly Detection Imputation +3

Towards Complex Dynamic Physics System Simulation with Graph Neural ODEs

no code implementations21 May 2023 Guangsi Shi, Daokun Zhang, Ming Jin, Shirui Pan, Philip S. Yu

To better comprehend the complex physical laws, this paper proposes a novel learning based simulation model- Graph Networks with Spatial-Temporal neural Ordinary Equations (GNSTODE)- that characterizes the varying spatial and temporal dependencies in particle systems using a united end-to-end framework.

LAVA: Data Valuation without Pre-Specified Learning Algorithms

1 code implementation28 Apr 2023 Hoang Anh Just, Feiyang Kang, Jiachen T. Wang, Yi Zeng, Myeongseob Ko, Ming Jin, Ruoxi Jia

(1) We develop a proxy for the validation performance associated with a training set based on a non-conventional class-wise Wasserstein distance between training and validation sets.

Data Valuation

Geometric Relational Embeddings: A Survey

no code implementations24 Apr 2023 Bo Xiong, Mojtaba Nayyeri, Ming Jin, Yunjie He, Michael Cochez, Shirui Pan, Steffen Staab

Geometric relational embeddings map relational data as geometric objects that combine vector information suitable for machine learning and structured/relational information for structured/relational reasoning, typically in low dimensions.

Hierarchical Multi-label Classification Knowledge Graph Completion +3

IP-FL: Incentivized and Personalized Federated Learning

no code implementations15 Apr 2023 Ahmad Faraz Khan, Xinran Wang, Qi Le, Zain ul Abdeen, Azal Ahmad Khan, Haider Ali, Ming Jin, Jie Ding, Ali R. Butt, Ali Anwar

Our approach enhances the personalized model appeal for self-aware clients with high-quality data leading to their active and consistent participation.

Clustering Personalized Federated Learning

Monte Carlo Grid Dynamic Programming: Almost Sure Convergence and Probability Constraints

1 code implementation10 Mar 2023 Mohammad S. Ramadan, Ahmad Al-Tawaha, Mohamed Shouman, Ahmed Atallah, Ming Jin

This paper presents a Monte Carlo-based sampling approach for the state space and an interpolation procedure for the resulting value function, dependent on the process noise density, in a "self-approximating" fashion, eliminating the need for ordering or set-membership tests.

Winning the CityLearn Challenge: Adaptive Optimization with Evolutionary Search under Trajectory-based Guidance

no code implementations4 Dec 2022 Vanshaj Khattar, Ming Jin

Modern power systems will have to face difficult challenges in the years to come: frequent blackouts in urban areas caused by high power demand peaks, grid instability exacerbated by intermittent renewable generation, and global climate change amplified by rising carbon emissions.

Decision Making Reinforcement Learning (RL) +1

On Solution Functions of Optimization: Universal Approximation and Covering Number Bounds

no code implementations2 Dec 2022 Ming Jin, Vanshaj Khattar, Harshal Kaushik, Bilgehan Sel, Ruoxi Jia

We study the expressibility and learnability of convex optimization solution functions and their multi-layer architectural extension.

Non-stationary Risk-sensitive Reinforcement Learning: Near-optimal Dynamic Regret, Adaptive Detection, and Separation Design

no code implementations19 Nov 2022 Yuhao Ding, Ming Jin, Javad Lavaei

We study risk-sensitive reinforcement learning (RL) based on an entropic risk measure in episodic non-stationary Markov decision processes (MDPs).

Reinforcement Learning (RL)

Hyper-Parameter Auto-Tuning for Sparse Bayesian Learning

no code implementations9 Nov 2022 Dawei Gao, Qinghua Guo, Ming Jin, Guisheng Liao, Yonina C. Eldar

Choosing the values of hyper-parameters in sparse Bayesian learning (SBL) can significantly impact performance.

Recognizing Nested Entities from Flat Supervision: A New NER Subtask, Feasibility and Challenges

no code implementations1 Nov 2022 Enwei Zhu, Yiyang Liu, Ming Jin, Jinpeng Li

However, existing nested NER models heavily rely on training data annotated with nested entities, while labeling such data is costly.

named-entity-recognition Named Entity Recognition +1

Variational Bayesian Inference Clustering Based Joint User Activity and Data Detection for Grant-Free Random Access in mMTC

no code implementations25 Oct 2022 Zhaoji Zhang, Qinghua Guo, Ying Li, Ming Jin, Chongwen Huang

Furthermore, in conjunction with the AMP algorithm, a variational Bayesian inference based clustering (VBIC) algorithm is developed to solve this clustering problem.

Bayesian Inference Clustering +1

Learning Neural Networks under Input-Output Specifications

no code implementations23 Feb 2022 Zain ul Abdeen, He Yin, Vassilis Kekatos, Ming Jin

In this paper, we examine an important problem of learning neural networks that certifiably meet certain specifications on input-output behaviors.

Multivariate Time Series Forecasting with Dynamic Graph Neural ODEs

2 code implementations17 Feb 2022 Ming Jin, Yu Zheng, Yuan-Fang Li, Siheng Chen, Bin Yang, Shirui Pan

Multivariate time series forecasting has long received significant attention in real-world applications, such as energy consumption and traffic prediction.

Multivariate Time Series Forecasting Time Series +1

Towards Graph Self-Supervised Learning with Contrastive Adjusted Zooming

no code implementations20 Nov 2021 Yizhen Zheng, Ming Jin, Shirui Pan, Yuan-Fang Li, Hao Peng, Ming Li, Zhao Li

To overcome the aforementioned problems, we introduce a novel self-supervised graph representation learning algorithm via Graph Contrastive Adjusted Zooming, namely G-Zoom, to learn node representations by leveraging the proposed adjusted zooming scheme.

Contrastive Learning Graph Representation Learning +1

Adversarial Unlearning of Backdoors via Implicit Hypergradient

2 code implementations ICLR 2022 Yi Zeng, Si Chen, Won Park, Z. Morley Mao, Ming Jin, Ruoxi Jia

Particularly, its performance is more robust to the variation on triggers, attack settings, poison ratio, and clean data size.

Spatiotemporal Representation Learning on Time Series with Dynamic Graph ODEs

no code implementations29 Sep 2021 Ming Jin, Yuan-Fang Li, Yu Zheng, Bin Yang, Shirui Pan

Spatiotemporal representation learning on multivariate time series has received tremendous attention in forecasting traffic and energy data.

Graph structure learning Representation Learning +2

Towards General Robustness to Bad Training Data

no code implementations29 Sep 2021 Tianhao Wang, Yi Zeng, Ming Jin, Ruoxi Jia

In this paper, we focus on the problem of identifying bad training data when the underlying cause is unknown in advance.

Data Summarization

Recurrent Neural Network Controllers Synthesis with Stability Guarantees for Partially Observed Systems

1 code implementation8 Sep 2021 Fangda Gu, He Yin, Laurent El Ghaoui, Murat Arcak, Peter Seiler, Ming Jin

Neural network controllers have become popular in control tasks thanks to their flexibility and expressivity.

LEMMA

Generative and Contrastive Self-Supervised Learning for Graph Anomaly Detection

1 code implementation23 Aug 2021 Yu Zheng, Ming Jin, Yixin Liu, Lianhua Chi, Khoa T. Phan, Yi-Ping Phoebe Chen

While the generative attribute regression module allows us to capture the anomalies in the attribute space, the multi-view contrastive learning module can exploit richer structure information from multiple subgraphs, thus abling to capture the anomalies in the structure space, mixing of structure, and attribute information.

Attribute Contrastive Learning +3

MS-MDA: Multisource Marginal Distribution Adaptation for Cross-subject and Cross-session EEG Emotion Recognition

1 code implementation16 Jul 2021 Hao Chen, Ming Jin, Zhunan Li, Cunhang Fan, Jinpeng Li, Huiguang He

Although several studies have adopted domain adaptation (DA) approaches to tackle this problem, most of them treat multiple EEG data from different subjects and sessions together as a single source domain for transfer, which either fails to satisfy the assumption of domain adaptation that the source has a certain marginal distribution, or increases the difficulty of adaptation.

Domain Adaptation EEG +2

A Unified Framework for Task-Driven Data Quality Management

no code implementations10 Jun 2021 Tianhao Wang, Yi Zeng, Ming Jin, Ruoxi Jia

High-quality data is critical to train performant Machine Learning (ML) models, highlighting the importance of Data Quality Management (DQM).

Data Summarization Data Valuation +1

Multi-Scale Contrastive Siamese Networks for Self-Supervised Graph Representation Learning

1 code implementation12 May 2021 Ming Jin, Yizhen Zheng, Yuan-Fang Li, Chen Gong, Chuan Zhou, Shirui Pan

To overcome this problem, inspired by the recent success of graph contrastive learning and Siamese networks in visual representation learning, we propose a novel self-supervised approach in this paper to learn node representations by enhancing Siamese self-distillation with multi-scale contrastive learning.

Contrastive Learning Graph Representation Learning

Controlling Smart Inverters using Proxies: A Chance-Constrained DNN-based Approach

no code implementations2 May 2021 Sarthak Gupta, Vassilis Kekatos, Ming Jin

The trained DNNs can be driven by partial, noisy, or proxy descriptors of the current grid conditions.

Unitary Approximate Message Passing for Sparse Bayesian Learning

no code implementations25 Jan 2021 Man Luo, Qinghua Guo, Ming Jin, Yonina C. Eldar, Defeng, Huang, Xiangming Meng

Sparse Bayesian learning (SBL) can be implemented with low complexity based on the approximate message passing (AMP) algorithm.

Variational Inference

Imitation Learning with Stability and Safety Guarantees

1 code implementation16 Dec 2020 He Yin, Peter Seiler, Ming Jin, Murat Arcak

A method is presented to learn neural network (NN) controllers with stability and safety guarantees through imitation learning (IL).

Imitation Learning

Power up! Robust Graph Convolutional Network based on Graph Powering

no code implementations25 Sep 2019 Ming Jin, Heng Chang, Wenwu Zhu, Somayeh Sojoudi

By challenging the classical graph Laplacian, we propose a new convolution operator that is provably robust in the spectral domain and is incorporated in the GCN architecture to improve expressivity and interpretability.

Adversarial Robustness

Power up! Robust Graph Convolutional Network via Graph Powering

1 code implementation24 May 2019 Ming Jin, Heng Chang, Wenwu Zhu, Somayeh Sojoudi

By challenging the classical graph Laplacian, we propose a new convolution operator that is provably robust in the spectral domain and is incorporated in the GCN architecture to improve expressivity and interpretability.

Adversarial Robustness

Stability-certified reinforcement learning: A control-theoretic perspective

no code implementations26 Oct 2018 Ming Jin, Javad Lavaei

We investigate the important problem of certifying stability of reinforcement learning policies when interconnected with nonlinear dynamical systems.

reinforcement-learning Reinforcement Learning +1

Inverse Reinforcement Learning via Deep Gaussian Process

no code implementations26 Dec 2015 Ming Jin, Andreas Damianou, Pieter Abbeel, Costas Spanos

We propose a new approach to inverse reinforcement learning (IRL) based on the deep Gaussian process (deep GP) model, which is capable of learning complicated reward structures with few demonstrations.

reinforcement-learning Reinforcement Learning +1

Environmental Sensing by Wearable Device for Indoor Activity and Location Estimation

no code implementations22 Jun 2014 Ming Jin, Han Zou, Kevin Weekly, Ruoxi Jia, Alexandre M. Bayen, Costas J. Spanos

We present results from a set of experiments in this pilot study to investigate the causal influence of user activity on various environmental parameters monitored by occupant carried multi-purpose sensors.

energy management Management +1

Cannot find the paper you are looking for? You can Submit a new open access paper.